High [CVE-2026-53374] zero-initialize GART table on allocation

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: zero-initialize GART table on allocation GART TLB is flushed after unmapping but not after mapping.

Since amdgpu_bo_create_kernel() does not zero-initialize the buffer, when a single PTE is written the TLB may speculatively load other uninitialized entries from the same cacheline. Those garbage entries can appear valid, and a subsequent write to another PTE in the same cacheline may cause the GPU to use a stale garbage PTE from the TLB.

Fix this by calling memset_io() to zero-initialize the GART table with gart_pte_flags immediately after allocation.

Using AMDGPU_GEM_CREATE_VRAM_CLEARED, SDMA-based clear will not work since SDMA needs GART to be initialized to work. (cherry picked from commit d9af8263b82b6eaa60c5718e0c6631c5037e4b24) A flaw was found in the Linux kernel's AMD GPU (amdgpu) driver. When allocating a Graphics Address Remapping Table (GART), the memory was not properly initialized.

This could allow a local attacker to potentially access uninitialized memory, leading to information disclosure or unexpected system behavior due to the GPU using stale data from its Translation Lookaside Buffer (TLB). Red Hat severity: Important — CVSS 7 (CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H).

Weakness: CWE-824.